Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    ://

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vets
    0.73
     angels
    0.71
     Angels
    0.68
     CPI
    0.67
     head
    0.66
    PTI
    0.66
     Psi
    0.65
     sensitive
    0.65
     ρ
    0.64
     γ
    0.63
    POSITIVE LOGITS
    Concent
    0.75
    concentration
    0.74
     Plo
    0.70
     Concentration
    0.70
    simple
    0.67
    Hand
    0.67
    órmula
    0.67
     నేపథ
    0.65
     бү
    0.63
     concentración
    0.63
    Act Density 0.001%

    No Known Activations